会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • COLOR UNMIXING AND REGION OF INTEREST DETECTION IN TISSUE SAMPLES
    • 组织样本中色彩的兴趣和兴趣区域的检测
    • WO2004111930A9
    • 2005-05-06
    • PCT/US2004016858
    • 2004-05-28
    • RABINOVICH ANDREW M
    • RABINOVICH ANDREW M
    • G06K9/00G06K9/46G06K9/62G06T20060101
    • G06K9/0014G06K9/00127G06K9/4619G06K9/624
    • In a method and system and machine-readable medium, colors in an image (200) are unmixed (202) using a matrix X = AS, where A is a ns. x nd matrix of spectral definitions, where s is the number of spectral components and d is the number of dyes into which the image is decomposed, and where S is a ns x l matrix of amounts of each dye at every pixel, where l is the number of pixels; the matrix X is constrained for solution by an unsupervised matrix decomposition method having constraints consistent with properties of an additive color model; and nd is determined. A texture is determined to identify areas of interest. Further processing may automatically measure cell dye concentration in the determined regions of interest.
    • 在方法和系统和机器可读介质中,图像(200)中的颜色使用矩阵X = AS而不混合(202),其中A是ns。 光谱定义的第x个矩阵,其中s是光谱分量的数量,d是图像分解成的染料的数量,其中S是每个像素处的每个染料的量的ns×1矩阵,其中l是 像素数; 通过具有与加性颜色模型的属性一致的约束的无监督矩阵分解方法来限制矩阵X的解; 并确定nd。 确定纹理以识别感兴趣的区域。 进一步的处理可以自动测量所确定的感兴趣区域中的细胞染料浓度。
    • 2. 发明申请
    • COLOR UNMIXING AND REGION OF INTEREST DETECTION IN TISSUE SAMPLES
    • 彩色人体组织样本和感兴趣区域检测
    • WO2004111930A3
    • 2005-03-24
    • PCT/US2004016858
    • 2004-05-28
    • RABINOVICH ANDREW M
    • RABINOVICH ANDREW M
    • G06K9/00G06K9/46G06K9/62G06T20060101
    • G06K9/0014G06K9/00127G06K9/4619G06K9/624
    • In a method and system and machine-readable medium, colors in an image (200) are unmixed (202) using a matrix X = AS, where A is a ns. x nd matrix of spectral definitions, where s is the number of spectral components and d is the number of dyes into which the image is decomposed, and where S is a ns x l matrix of amounts of each dye at every pixel, where l is the number of pixels; the matrix X is constrained for solution by an unsupervised matrix decomposition method having constraints consistent with properties of an additive color model; and nd is determined. A texture is determined to identify areas of interest. Further processing may automatically measure cell dye concentration in the determined regions of interest.
    • 在方法和系统以及机器可读介质中,使用矩阵X = AS将图像(200)中的颜色解混(202),其中A是ns。 x是光谱定义的矩阵,其中s是光谱分量的数量,并且d是图像被分解成的染料的数量,并且其中S是在每个像素处的每种染料的量的ns×1矩阵,其中l是 像素数量; 通过具有与加性颜色模型的性质一致的约束的无监督矩阵分解方法来约束矩阵X以求解; 并且nd被确定。 纹理被确定以识别感兴趣的区域。 进一步处理可以自动测量所确定的感兴趣区域中的细胞染料浓度。